Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    a bit of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     élevé
    0.41
     teasing
    0.41
     ausger
    0.41
    ਂ
    0.40
     মজার
    0.39
     wiser
    0.39
    proud
    0.38
     brag
    0.38
     БД
    0.38
    )),
    0.37
    POSITIVE LOGITS
     of
    0.49
     Dien
    0.47
     Relatively
    0.47
     relatively
    0.46
    of
    0.46
     pf
    0.46
     ofthe
    0.44
     relativamente
    0.44
    ของการ
    0.43
     comparatively
    0.42
    Act Density 0.018%

    No Known Activations